Facing undermodelling in sign-perturbed-sums system identification

DOI10.1016/j.sysconle.2021.104936zbMath1475.93033OpenAlexW3157851059MaRDI QIDQ2242890

Balázs Csanád Csáji, Marco C. Campi, Algo Carè, Erik Weyer

Publication date: 10 November 2021

Published in: Systems \& Control Letters (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.sysconle.2021.104936

zbMATH Keywords

system identificationleast squaresconfidence regionsfinite sample resultsuncertainty evaluationdistribution-free results

Mathematics Subject Classification ID

System identification (93B30) Linear systems in control theory (93C05)

Related Items (3)

Non-asymptotic state-space identification of closed-loop stochastic linear systems using instrumental variables ⋮ Bayesian frequentist bounds for machine learning and system identification ⋮ A simple condition for the boundedness of sign-perturbed-sums (SPS) confidence regions

Cites Work

• Unnamed Item
• Kernel methods in system identification, machine learning and function estimation: a survey
• Unified set membership theory for identification, prediction and filtering of nonlinear systems
• On covariance function tests used in system identification
• Non-asymptotic confidence regions for model parameters in the presence of unmodelled dynamics
• Choosing the best model: Level of detail, complexity, and model performance
• On approximation of stable linear dynamical systems using Laguerre and Kautz functions
• Design of experiments for nonlinear system identification: a set membership approach
• The nonasymptotic confidence set for parameters of a linear control object under an arbitrary external disturbance
• Non-asymptotic confidence regions for the parameters of EIV systems
• Distribution-free uncertainty quantification for kernel methods by gradient perturbations
• Perturbed datasets methods for hypothesis testing and structure of corresponding confidence sets
• Asymptotic properties of SPS confidence regions
• Parameter identification for nonlinear systems: guaranteed confidence regions through LSCR
• Guaranteed non-asymptotic confidence regions in system identification
• \(H_{\infty}\) set membership identification: a survey
• Guaranteed characterization of exact non-asymptotic confidence regions as defined by LSCR and SPS
• Randomized Control Strategies Under Arbitrary External Noise
• Probabilistic Optimal Estimation With Uniformly Distributed Noise
• System identification using Laguerre models
• A unifying construction of orthonormal bases for system identification
• Sign-Perturbed Sums: A New System Identification Approach for Constructing Exact Non-Asymptotic Confidence Regions in Linear Regression Models
• On estimation of errors caused by non-linear undermodelling in system identification
• A shift in paradigm for system identification
• A Note on the Numerical Solutions of Kernel-Based Learning Problems

This page was built for publication: Facing undermodelling in sign-perturbed-sums system identification